Full Curriculum — 14 Free + 10 Premium Days
Each day bridges a software engineering concept to its AI equivalent.
Week 1Think Like an AI Engineer
LLM APIs, Structured Output & Streaming
You already call REST APIs and parse JSON. Today you'll call LLM APIs the same way — but you'll also learn the two killer features every AI app needs: extracting typed JSON from LLMs (structured output) and streaming responses in real-time. By tonight, you'll ship a code review tool you'll actually use at work.
Ship: AI code review tool
Embeddings & Vector Search
SQL LIKE matches characters. Vector search matches meaning. You'll learn how embeddings turn text into numbers, build similarity search from scratch, and understand when to use Pinecone, pgvector, or Chroma. You'll ship a search engine that finds 'cozy sneakers' when users type 'comfortable shoes'.
Ship: Semantic search engine
RAG Deep Dive
RAG is the #1 AI pattern in production. You'll go far beyond basics — learn multiple chunking strategies, debug retrieval failures, handle the #1 cause of hallucination (bad retrieval), and build a Q&A system that cites its sources. This is the day that separates AI engineers from tutorial followers.
Ship: Document Q&A system
Function Calling & Tool Chains
You define REST endpoints with schemas. Function calling is the same — you define tools with Zod schemas and the LLM decides when to call them. Today you'll go beyond single tool calls: parallel execution, error recovery, and multi-step tool chains where one tool's output feeds another.
Ship: AI assistant with live tools
AI Agents & Orchestration
State machines have predefined transitions. Agents decide autonomously. You'll implement multiple agent patterns (ReAct, plan-and-execute, tool-use), add safety guardrails against infinite loops and cost runaway, and build a research agent that gathers, summarizes, and compares information.
Ship: Research automation agent
Multimodal AI & Streaming UX
You handle file uploads. Now you'll make AI understand them — extracting structured JSON from images, analyzing documents, and processing audio. Plus, you'll master the UX patterns that make AI apps feel magical: streaming responses, optimistic UI, and progressive loading.
Ship: Receipt scanner + streaming chat
Capstone: AI Documentation Assistant
Combine everything from Week 1 into a real AI product: an AI documentation assistant. It uses RAG to answer questions from docs, tools to search and navigate, streaming for real-time UX, and structured output for formatted responses. This is your first portfolio-grade AI project.
Ship: AI docs assistant (portfolio piece)
Week 2Ship Like an AI Engineer
AI Evaluation & Testing
Unit tests check exact outputs. LLMs are non-deterministic — same input, different output every time. You need evals: automated quality checks using rubrics, LLM-as-judge, and eval datasets. You'll learn eval-driven development — write evals first, then iterate prompts to pass them.
Ship: Eval suite for your RAG app
Security & Guardrails
Prompt injection is SQL injection 2.0. You'll build defense-in-depth: input sanitization, structured prompts, output validation, PII detection, and content filtering. Then you'll try to break your own Day 7 capstone — because if you can't hack it, someone else will.
Ship: Hardened AI endpoint
Cost Optimization & Multi-Model Strategy
AI API costs can explode overnight. You'll learn the same cost controls you use for infrastructure — caching, routing, and optimization — adapted for AI. Semantic caching, model routing (fast/cheap vs slow/smart), multi-model strategy (GPT-4o vs Claude vs open-source), and token optimization.
Ship: Multi-model router with caching
LLMOps & Observability
You use APM to monitor APIs. LLMOps adds AI-specific observability: prompt tracing, token usage tracking, latency per model, quality scores, and cost dashboards. You'll integrate real tools (Langfuse) and learn what to log, trace, and alert on in production AI systems.
Ship: Observable AI pipeline
Fine-tuning & Model Customization
When should you fine-tune vs prompt-engineer vs use RAG? Most teams get this wrong. You'll build the decision framework, then practice each approach: optimize prompts first (cheap), add RAG for domain knowledge (medium), and fine-tune only when needed (expensive). By the end you'll know exactly which tool to reach for.
Ship: Decision framework + fine-tuned classifier
Adding AI to Existing Apps
The #1 question devs ask: 'I have an existing app — how do I add AI?' Today you'll learn the patterns: AI-powered search, smart autocomplete, content generation, automated tagging, and intelligent routing. You'll take a standard Next.js CRUD app and add 3 AI features without rewriting anything.
Ship: AI features in an existing Next.js app
Capstone: AI Codebase Q&A
Build your portfolio centerpiece: an AI-powered codebase Q&A tool. It indexes a GitHub repo, answers questions about the code using RAG, includes evals for quality, guard rails for safety, observability for monitoring, and multi-model routing for cost control. This is the project that gets you hired.
Ship: AI codebase Q&A (portfolio centerpiece)
Week 3Master Advanced AIPremium
Multi-Agent Systems & Crew Architectures
You design microservices where each service has a single responsibility and they communicate via APIs. Multi-agent systems work the same way — each agent has a role (researcher, writer, reviewer) and they collaborate via message passing. You'll build agent crews that divide-and-conquer complex tasks.
Ship: Multi-agent research team
Advanced RAG: Hybrid Search, Re-ranking & Query Decomposition
Basic RAG retrieves top-K chunks. Production RAG combines keyword search (BM25) with vector search, re-ranks results with cross-encoders, decomposes complex queries into sub-queries, and uses metadata filtering. You'll build the RAG pipeline that actually works in production.
Ship: Production RAG with hybrid search
AI System Design for Interviews
You've prepared for system design interviews. AI system design adds new dimensions: model selection, prompt architecture, RAG vs fine-tuning decisions, eval strategies, cost budgets, and latency-quality tradeoffs. You'll practice the framework that top AI companies use in interviews.
Ship: 3 AI system design solutions
Building AI Products from 0→1
You write product specs. AI products need additional sections: model capability assessment, failure mode analysis, eval criteria, human-in-the-loop design, and cost modeling. You'll learn the product thinking that separates senior AI engineers from prompt wranglers.
Ship: AI product spec + prototype
Voice & Realtime AI
You build WebSocket apps for real-time features. Voice AI uses the same patterns — persistent connections, streaming bidirectional data, and event-driven architecture. You'll integrate speech-to-text, text-to-speech, and build conversational AI that responds in real time.
Ship: Voice-powered AI assistant
Week 4Ship & Get CertifiedPremium
AI Workflows with LangGraph & CrewAI
CI/CD pipelines have stages, conditions, and parallel branches. AI workflow frameworks (LangGraph, CrewAI) provide the same abstractions for agent orchestration — nodes, edges, conditional routing, and state management. You'll build production workflows that go far beyond linear chains.
Ship: Complex AI workflow with branching
Custom Model Serving & Self-Hosting
You deploy containerized services. Self-hosting AI models is the same — Docker containers running model servers (Ollama, vLLM) behind load balancers. You'll learn when self-hosting beats APIs (privacy, cost at scale, latency), and set up a complete model serving stack.
Ship: Self-hosted model with API endpoint
AI-Powered Internal Tools & Automations
Every team has internal tools and manual processes. AI can supercharge them: auto-categorize support tickets, summarize meeting notes, generate release notes from PRs, auto-triage bugs, and build intelligent Slack bots. You'll build practical AI automations your team will actually use.
Ship: AI internal tool for your team
Capstone: Production Multi-Agent System
Combine everything from Weeks 3-4 into your most impressive portfolio piece: a production multi-agent system with specialized agents, hybrid RAG retrieval, workflow orchestration, observability, and cost optimization. This is the project that demonstrates senior-level AI engineering.
Ship: Multi-agent system (portfolio piece)
AI Career Playbook — Portfolio, Resume & Interview Prep
You've completed the full curriculum and mastered AI engineering. Now package it for your career: build a portfolio site showcasing your best projects, craft an AI-engineer resume that stands out, and practice the technical interview questions that top companies ask. This day gets you hired.
Ship: Complete AI portfolio + resume